Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to significance, importance, or influence

    oai_token-act-pair · gpt-3.5-turbo

    references to the consequences or significance of various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bows
    -0.81
    fighters
    -0.73
    few
    -0.71
    cop
    -0.71
    bow
    -0.71
    gio
    -0.70
    bug
    -0.69
    vez
    -0.69
    bones
    -0.68
    Interstitial
    -0.67
    POSITIVE LOGITS
     implications
    1.03
     ramifications
    0.96
    romeda
    0.89
     repercussions
    0.77
    notation
    0.76
     fallout
    0.76
    uality
    0.75
     consequential
    0.75
    earable
    0.74
     impact
    0.74
    Act Density 0.039%

    No Known Activations